Just flagging this post which has some advice how to get "from zero to hero": Levelling Up in AI Safety Research Engineering. According to this framework, I went to Level 3.
Hi Henry :) Thanks a lot for your kind words - and for sharing your thoughts and resources on the topic! I am very grateful you've commented on the post as someone with a technological background. Will definitely have a look at them myself as well.
RE maths: I think I do understand the basics. We had pretty much of that at highschool and the statistics courses included a lot of mathematics as well (especially probabilities). So I agree that you probably need some knowledge here, but maybe this is the reason why I didn't need to go deeper(?)
This was a really interesting decision, thanks for highlighting it here! In the meantime it was followed by other courts with similar cases in the Netherlands and Australia.
Also, for people interested in a legal analysis of the decision, together with my colleague Renan Araújo from the Legal Priorities Project I wrote a blog post on the decision for a UK blog.
Some considerations I came to think about which might prevent AI systems from becoming power-seeking by default:
So even if AI systems make plans / chose actions based on expected value calculations, just doing the thing they are trying to do might be the better strategy. ... (read more)